Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

2025-05-24

AI Summary

In time series forecasting, single models often lack robust generalization across diverse samples and suffer from model isolation. To address this, we propose TimeFuse—a novel framework for sample-level adaptive fusion of heterogeneous forecasting models. TimeFuse introduces a lightweight fusor network that extracts meta-features and learns differentiable, sample-specific fusion weights. It supports joint meta-training across multiple datasets and enables zero-shot cross-dataset transfer. Extensive experiments on both long-term and short-term forecasting tasks demonstrate that TimeFuse consistently outperforms state-of-the-art single-model baselines, delivering near-universal performance gains. It significantly reduces dependency on manual model selection and establishes a general-purpose, model-agnostic fusion paradigm for time series forecasting.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Diffusion Models for Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark datasets, through a fine-grained sample-level inspection, we find that (i) no single model consistently outperforms others across different test samples, but instead (ii) each model excels in specific cases. These findings prompt us to explore how to adaptively leverage the distinct strengths of various forecasting models for different samples. We introduce TimeFuse, a framework for collective time-series forecasting with sample-level adaptive fusion of heterogeneous models. TimeFuse utilizes meta-features to characterize input time series and trains a learnable fusor to predict optimal model fusion weights for any given input. The fusor can leverage samples from diverse datasets for joint training, allowing it to adapt to a wide variety of temporal patterns and thus generalize to new inputs, even from unseen datasets. Extensive experiments demonstrate the effectiveness of TimeFuse in various long-/short-term forecasting tasks, achieving near-universal improvement over the state-of-the-art individual models. Code is available at https://github.com/ZhiningLiu1998/TimeFuse.

Problem

• Adaptively combine strengths of diverse forecasting models
• Improve accuracy via sample-level fusion of time-series models
• Generalize across datasets with meta-feature-based model fusion

Innovation

• Adaptive fusion of heterogeneous models
• Meta-features characterize input time series
• Learnable fusor predicts optimal model weights